Tap a claim on the ring to put it at the centre.
← Designers should be designing right at the boundary of the current…
17 connected korrents · 15 moments from 15 Nov 2023 to 24 Sept 2026. Nearly all of them are about vibe coding .
Everything filed under design
design
Everything filed under LLMs
LLMs Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Read this korrent: Designers should be designing right at the boundary of the current model, hoping the next one solves it; understanding what is possible and pushing the edges even if you get stuck is probably a good place to be right now. Designers should be designing right at the boundary of the current model, hoping the next one solves it; understanding what is possible and pushing the edges even if you get stuck is probably a good place to be right now. Last stated 6 months ago
14 Apr 2026
BL
Brian Lovin — holds since 2026-04-14 — tap for who they are
Same subject: Deciding what software should do and why is still a human job: vibe coding changes the implementation phase far more than the planning phase. — tap to centre the map on it Deciding what software should do and why is still a human job: vibe coding changes the implementation phase far more than the planning phase. Last stated 2 years ago
7 Mar 2025
JN
Jakob Nielsen — holds since 2025-03-07 — tap for who they are
Same subject: Making coding easy makes design more critical, not less: when anyone can produce working features, the quality of the experience is what sets products apart. — tap to centre the map on it Making coding easy makes design more critical, not less: when anyone can produce working features, the quality of the experience is what sets products apart. Last stated 2 years ago
7 Mar 2025
JN
Jakob Nielsen — holds since 2025-03-07 — tap for who they are
Same subject: Mockups existed because coding was hard; now designers can skip static mockups and go straight to building a UI that works. — tap to centre the map on it Mockups existed because coding was hard; now designers can skip static mockups and go straight to building a UI that works. Last stated 2 years ago
7 Mar 2025
JN
Jakob Nielsen — holds since 2025-03-07 — tap for who they are
Same subject: Vibe coding lets users design and build their own software, upending the user-centred design paradigm that has held since 1947. — tap to centre the map on it Vibe coding lets users design and build their own software, upending the user-centred design paradigm that has held since 1947. Last stated 2 years ago
13 Mar 2025
JN
Jakob Nielsen — holds since 2025-03-13 — tap for who they are
Same subject: A person at maximum vibe-coding speed has about three productive hours a day, and a company that will not let them stop there is going to break. — tap to centre the map on it A person at maximum vibe-coding speed has about three productive hours a day, and a company that will not let them stop there is going to break. Last stated 7 months ago
11 Mar 2026
SY
Steve Yegge — holds since 2026-03-11 — tap for who they are
Same subject: A vibe-coded codebase grows heresies: wrong ideas that take root among the agents, keep coming back, and are very hard to weed out. — tap to centre the map on it A vibe-coded codebase grows heresies: wrong ideas that take root among the agents, keep coming back, and are very hard to weed out. Last stated 7 months ago
11 Mar 2026
SY
Steve Yegge — holds since 2026-03-11 — tap for who they are
Same subject: Leaving a known production bug unfixed is the right call when the business impact is zero — my vibe-coded service crashes and still has fewer outages than LeetCode. — tap to centre the map on it Leaving a known production bug unfixed is the right call when the business impact is zero — my vibe-coded service crashes and still has fewer outages than LeetCode. Last stated 3 months ago
24 Jun 2026
NE
NeetCode — holds since 2026-06-24 — tap for who they are
Same subject: Letting non-programmers vibe-code features into a large existing product destroys its architecture, even when every individual change looks defensible. — tap to centre the map on it Letting non-programmers vibe-code features into a large existing product destroys its architecture, even when every individual change looks defensible. Last stated a month ago
26 Aug 2026
DH
David Heinemeier Hansson — holds since 2026-08-26 — tap for who they are
Same subject: A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI. — tap to centre the map on it A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI. Last stated 9 months ago
1 Jan 2026
JL
Jason Lemkin — holds since 2026-01-01 — tap for who they are
Same subject: A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. — tap to centre the map on it A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. Last stated 3 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: A body of publications is easy for AI models to consume via pretraining corpora but cumbersome for most humans due to CAPTCHAs, accounts, and paywalls. — tap to centre the map on it A body of publications is easy for AI models to consume via pretraining corpora but cumbersome for most humans due to CAPTCHAs, accounts, and paywalls. Last stated 3 weeks ago
17 Sept 2026
PC
Patrick Collison — holds since 2026-09-17 — tap for who they are
Same subject: In instruction tuning, a smaller set of high-quality training examples outperforms a larger, noisier dataset. — tap to centre the map on it In instruction tuning, a smaller set of high-quality training examples outperforms a larger, noisier dataset. Last stated 3 years ago
15 Nov 2023
SR
Sebastian Ruder — holds since 2023-11-15 — tap for who they are
Same subject: There is unmet demand for a single, well-integrated local AI model experience, rather than a patchwork of local AI components. — tap to centre the map on it There is unmet demand for a single, well-integrated local AI model experience, rather than a patchwork of local AI components. Last stated 5 months ago
14 May 2026
SS
Salvatore Sanfilippo — holds since 2026-05-14 — tap for who they are
Same subject: When pre-training data is limited, it is better to train a smaller model for multiple epochs than to train a larger model on unique data once. — tap to centre the map on it When pre-training data is limited, it is better to train a smaller model for multiple epochs than to train a larger model on unique data once. Last stated 3 years ago
1 Dec 2023
SR
Sebastian Ruder — holds since 2023-12-01 — tap for who they are
Same subject: A skill is basically a prompt, sometimes a large one, more like a style guide: the best practice for taste, which font to use, and how to guide AI not to create AI slop. — tap to centre the map on it A skill is basically a prompt, sometimes a large one, more like a style guide: the best practice for taste, which font to use, and how to guide AI not to create AI slop. Last stated 3 months ago
30 Jun 2026
MT
Meng To — holds since 2026-06-30 — tap for who they are
Same subject: Agents are good at producing output but not at judging which output is worth producing in the first place. — tap to centre the map on it Agents are good at producing output but not at judging which output is worth producing in the first place. Last stated 2 weeks ago
24 Sept 2026
KD
Kent C. Dodds — holds since 2026-09-24 — tap for who they are
Same subject: AI has no genuine discernment; it absorbs and reproduces without judgment. — tap to centre the map on it AI has no genuine discernment; it absorbs and reproduces without judgment. Last stated 2 months ago
10 Aug 2026
AH
Ann Handley — holds since 2026-08-10 — tap for who they are
At the centre
Designers should be designing right at the boundary of the current model, hoping the next one solves it; understanding what is possible and pushing the edges even if you get stuck is probably a good place to be right now.
Holds Read this korrent →
Deciding what software should do and why is still a human job: vibe coding changes the implementation phase far more than the planning phase.
Holds
Making coding easy makes design more critical, not less: when anyone can produce working features, the quality of the experience is what sets products apart.
Holds
Mockups existed because coding was hard; now designers can skip static mockups and go straight to building a UI that works.
Holds
Vibe coding lets users design and build their own software, upending the user-centred design paradigm that has held since 1947.
Holds
A person at maximum vibe-coding speed has about three productive hours a day, and a company that will not let them stop there is going to break.
Holds
A vibe-coded codebase grows heresies: wrong ideas that take root among the agents, keep coming back, and are very hard to weed out.
Holds
Leaving a known production bug unfixed is the right call when the business impact is zero — my vibe-coded service crashes and still has fewer outages than LeetCode.
Holds
Letting non-programmers vibe-code features into a large existing product destroys its architecture, even when every individual change looks defensible.
Holds
A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI.
Holds
A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to.
Holds
A body of publications is easy for AI models to consume via pretraining corpora but cumbersome for most humans due to CAPTCHAs, accounts, and paywalls.
Holds
In instruction tuning, a smaller set of high-quality training examples outperforms a larger, noisier dataset.
Holds
There is unmet demand for a single, well-integrated local AI model experience, rather than a patchwork of local AI components.
Holds
When pre-training data is limited, it is better to train a smaller model for multiple epochs than to train a larger model on unique data once.
Holds
A skill is basically a prompt, sometimes a large one, more like a style guide: the best practice for taste, which font to use, and how to guide AI not to create AI slop.
Holds
Agents are good at producing output but not at judging which output is worth producing in the first place.
Holds
AI has no genuine discernment; it absorbs and reproduces without judgment.
Holds